LiquidAI

LFM 2.5 350M Mirai-L

trymirai/LFM2.5-350M-L
Vendor
LiquidAI
Quantization
Mirai-L
Parameters
350M
Size
354.8 MB
$ brew install mirai$ mirai --model trymirai/LFM2.5-350M-L

Benchmarks

882 tok/s

The speed at which text appears on screen

higher is better

38153 tok/s

How fast the model reads the prompt

higher is better

0.46 GB

RAM the model uses while running

lower is better

64.9 mJ/t

How much battery each generated token costs

lower is better

Benchmarked 26 Aug 2026

Integrate with SDK

1
Choose framework
2
Run the following command to install Mirai SDK
https://github.com/trymirai/uzu-swift
3
Apply code
1import Foundation2import Uzu34public func runChat() async throws {5    let engineConfig = EngineConfig.create()6    let engine = try await Engine.create(config: engineConfig)7    8    guard let model = try await engine.model(identifier: "alibaba:qwen3.5:0.8b:mirai:mirai-m:4") else {9        return10    }11    for try await update in try await engine.download(model: model).iterator() {12        print(String(format: "\r\u{001B}[2KDownload progress: %.2f%%", update.progress() * 100), terminator: "")13        fflush(stdout)14    }15    print()16    17    let messages = [18        ChatMessage.system().withText(text: "You are a helpful assistant"),19        ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")20    ]21    let session = try await engine.chat(model: model, config: .create())22    let stream = await session.replyWithStream(input: messages, config: .create())23    var message: ChatMessage? = nil24    for try await update in stream.iterator() {25        switch update {26        case .replies(let replies):27            let reply = replies.last28            message = reply?.message29            print("Generated tokens: \(reply?.stats.tokensCountOutput ?? 0)")30        case .error(let error):31            print("Error: \(error)")32        }33    }34    print("Reasoning: \(message?.reasoning() ?? "empty")")35    print("Text: \(message?.text() ?? "empty")")36}37

Details

Mirai's LFM2.5-350M Large Quantization

A large, high-quality 8-bit quantization of LiquidAI's compact LFM2.5-350M model, prepared for efficient local inference on Apple silicon. Mirai Large uses symmetric integer quantization with bfloat16 scales and group size 64, plus block-diagonal Random Hadamard Transforms with block size 32 to reduce activation and weight outliers. The checkpoint was prepared with post-training quantization.

sh
brew install mirai
mirai --model trymirai/LFM2.5-350M-L

Currently only Apple silicon inference is supported. See the Hugging Face model card and Mirai API documentation.

Explore all local models